So i am doing my first berttoken classifier. I am using a german polyglot dataset meaning tokenised words and lists of ner labels. a row is [‘word1’,‘word2’…] [‘ORG’,‘LOC’…] This is my code tokenizer = BertTokenizer.from_pretrained('bert-base-german-cased') encoded_dataset = [tokenizer(item['wor…

Loss error for bert token classifier

emmakelo December 3, 2021, 8:37am 5

Try putting num_train_epoch to flioat number = 1.0 to see if it works and also check the number of label? if it really 1 label in your training data ?

Topic		Replies	Views
Token classification on custom BERT and data Intermediate	2	1500	December 28, 2020
Expected scalar type Long but found Float using Trainer for BertForTokenClassification Beginners	6	4000	April 22, 2021
Expected input batch_size (2048) to match target batch_size (4) Beginners	3	1608	May 23, 2022
KeyError: 'loss' while training QnA Beginners	2	2556	March 17, 2022
KeyError: 'input_ids'. when training BERT with Trainer Models	5	7677	July 21, 2021

Loss error for bert token classifier

Related topics